# General Tasks on GPQA Diamond Source: [General Tasks on GPQA Diamond]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:51.539Z Evaluation of model performance on the GPQA Diamond dataset focusing on General Tasks, measured by PAQ and F1 scores. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | General Tasks | | Dataset (including any stated split) | GPQA Diamond | | Metric | PAQ Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 14 of 14 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [PAQ Score](): Higher is better; unit: SCALAR. - [F1 Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | PAQ Score | Result date | Report paper | | --- | --- | --- | --- | | UCPO | 0.677 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 0.6509 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 0.64 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 0.6025 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO | 0.5935 | Not recorded | 69802f68a8b01e76cc8e14db | | Prompt-UC | 0.5684 | Not recorded | 69802f68a8b01e76cc8e14db | | Baseline | 0.5657 | Not recorded | 69802f68a8b01e76cc8e14db | | UCPO | 0.3602 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 0.3432 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 0.3421 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 0.2946 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO | 0.2727 | Not recorded | 69802f68a8b01e76cc8e14db | | Prompt-UC | 0.2328 | Not recorded | 69802f68a8b01e76cc8e14db | | Baseline | 0.2256 | Not recorded | 69802f68a8b01e76cc8e14db | ### UCPO PAQ Score: 0.677. Result ID: 699615925698665ec4552151. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### GRPO-UC PAQ Score: 0.6509. Result ID: 699615925698665ec455214f. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B","Reward Coefficient (ru)":0.5}. This record does not assert independent reproduction. ### GRPO-UC PAQ Score: 0.64. Result ID: 699615925698665ec4552150. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B","Reward Coefficient (ru)":0.8}. This record does not assert independent reproduction. ### GRPO-UC PAQ Score: 0.6025. Result ID: 699615925698665ec455214e. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B","Reward Coefficient (ru)":0.2}. This record does not assert independent reproduction. ### GRPO PAQ Score: 0.5935. Result ID: 699615925698665ec455214d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### Prompt-UC PAQ Score: 0.5684. Result ID: 699615925698665ec455214c. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### Baseline PAQ Score: 0.5657. Result ID: 699615925698665ec455214b. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### UCPO PAQ Score: 0.3602. Result ID: 699615925698665ec4552158. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### GRPO-UC PAQ Score: 0.3432. Result ID: 699615925698665ec4552157. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B-Instruct","Reward Coefficient (ru)":0.8}. This record does not assert independent reproduction. ### GRPO-UC PAQ Score: 0.3421. Result ID: 699615925698665ec4552156. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B-Instruct","Reward Coefficient (ru)":0.5}. This record does not assert independent reproduction. ### GRPO-UC PAQ Score: 0.2946. Result ID: 699615925698665ec4552155. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B-Instruct","Reward Coefficient (ru)":0.2}. This record does not assert independent reproduction. ### GRPO PAQ Score: 0.2727. Result ID: 699615925698665ec4552154. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Prompt-UC PAQ Score: 0.2328. Result ID: 699615925698665ec4552153. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Baseline PAQ Score: 0.2256. Result ID: 699615925698665ec4552152. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.